langleu/qmd-query-expansion-lfm2.5-1.2b-instruct-v1-verbose

langleu/qmd-query-expansion-lfm2.5-1.2b-instruct-v1-verbose

LiquidAI/LFM2.5-1.2B-Instruct fine-tuned with LoRA for QMD query expansion using the v1-style verbose distillation data recipe. This repository contains the merged BF16 Transformers checkpoint at its root and QMD-ready GGUF quantizations alongside it.

Repository formats

• —Merged BF16 Transformers checkpoint: load the repository directly with AutoModelForCausalLM.from_pretrained("langleu/qmd-query-expansion-lfm2.5-1.2b-instruct-v1-verbose", torch_dtype=torch.bfloat16).
• —GGUF for QMD/llama.cpp: qmd-query-expansion-lfm2.5-1.2b-instruct-verbose-q5_k_m.gguf

The BF16 checkpoint is the unquantized merged fine-tune. The GGUF files are derived from that same merged checkpoint.

Artifact validated by this publishing invocation

• —File: qmd-query-expansion-lfm2.5-1.2b-instruct-verbose-q5_k_m.gguf
• —Kind: GGUF
• —Size: 843,354,528 bytes
• —SHA-256: 26a2e57d78c6bbd35da9cd720e09e4907df49c0b2003d4fe4beee24b21e2dfd1
• —Base model: `LiquidAI/LFM2.5-1.2B-Instruct`
• —Base revision: 868df74dd56ff8a0c2ac5dbf281690c2dbebe4c9
• —Dataset: `tobil/qmd-query-expansion-train`
• —Dataset revision: b3f2387077f3f0be5cd83689242783bbda1d983f
• —Configured release quantizations: Q5KM
• —Evaluation report: qmd-q5-scored

Prompt and behavior

/no_think Expand this search query: {query}

This variant emits a deliberately verbose seven-line expansion: one hyde:, three lex:, and three vec: lines. It was not trained for Query intent: or /only:* directives.

Each emitted line begins with lex:, vec:, or hyde:.

Use with QMD

The Transformers checkpoint is not loaded by QMD directly; select one of the GGUF files.

For a private repository, authenticate once with hf auth login, or set HF_TOKEN. QMD's node-llama-cpp downloader reads the cached Hugging Face token from ~/.cache/huggingface/token by default.

export QMD_GENERATE_MODEL="hf:langleu/qmd-query-expansion-lfm2.5-1.2b-instruct-v1-verbose/qmd-query-expansion-lfm2.5-1.2b-instruct-verbose-q5_k_m.gguf"
qmd query --json --explain --no-rerank "docker container shutdown timeout"

Training-data provenance

The public historical query set was used as the source of queries. Because it does not contain the unpublished labels used to train Tobil's Qwen3 release, labels were reconstructed locally by teacher distillation from `tobil/qmd-query-expansion-1.7B` Q5KM. Accepted teacher outputs were quality-scored, deduplicated, and split into 4,630 training and 516 untouched validation examples.

• —Teacher: tobil/qmd-query-expansion-1.7B Q5_K_M
• —Teacher recipe: 1 hyde + 3 lex + 3 vec; no intent or /only:* conditioning

Validation

• —Average QMD reward: 97.39%
• —Format compliance: 99.42%
• —Entity preservation: 100.00%
• —Hard failures: 0
• —Median QMD query-expansion latency: 0.959 s
• —p95 QMD query-expansion latency: 1.239 s

BF16 and GGUF comparison

Quality changes are reported in percentage points (pp), not relative percent. Small positive GGUF deltas can occur because sampled generation is not bit-for-bit deterministic.

• —BF16 (batched Transformers): approximately 481.7 output tokens/s and 3.30 examples/s.
• —Q5_K_M through QMD: 0.959 s median and 1.239 s p95 query-expansion latency.

Speed percentages are intentionally not reported. BF16 was measured with batched Transformers inference, while QMD runs GGUF through llama.cpp one query at a time. Their observed throughput and latency are useful operational measurements, but dividing them would not be an apples-to-apples speedup.

Credits

• —Liquid AI for LFM2.5 and the LFM Open License v1.0.
• —Tobi for QMD, the QMD query-expansion datasets, evaluation/scoring design, and the Qwen3 query-expansion model.
• —OrcsRise for the earlier LFM2 QMD fine-tuning work that informed the LFM target-module recipe.
• —QMD, TRL, PEFT, and llama.cpp.

Licensing and dataset notice

This derivative is governed by the LFM Open License v1.0. The included LICENSE must be retained, including its attribution and commercial-use terms.

The upstream QMD dataset card did not declare an explicit dataset license at the pinned revision. This repository records that fact and does not imply that a license was granted. Users and redistributors are responsible for confirming that their use is authorized. The verbose v1-style variant also discloses its Tobil Qwen3 teacher provenance above.